all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -0.6083555221557617,
    "eval_logits/rejected": -0.6260062456130981,
    "eval_logps/chosen": -439.2254638671875,
    "eval_logps/rejected": -623.379150390625,
    "eval_loss": 0.4394327700138092,
    "eval_rewards/accuracies": 0.8285714387893677,
    "eval_rewards/chosen": -1.7328646183013916,
    "eval_rewards/margins": 1.7488988637924194,
    "eval_rewards/rejected": -3.4817633628845215,
    "eval_runtime": 204.9828,
    "eval_samples": 4461,
    "eval_samples_per_second": 21.763,
    "eval_steps_per_second": 0.341,
    "total_flos": 0.0,
    "train_loss": 0.5098277106738136,
    "train_runtime": 16630.655,
    "train_samples": 133368,
    "train_samples_per_second": 8.019,
    "train_steps_per_second": 0.251
}